Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of preferences or favorites

    oai_token-act-pair · gpt-3.5-turbo

    statements that declare preferences or favorites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ideos
    -0.77
    ewitness
    -0.70
    isms
    -0.69
    ples
    -0.68
    assetsadobe
    -0.68
    Previous
    -0.68
    know
    -0.67
    ventures
    -0.67
    issues
    -0.66
    imeters
    -0.64
    POSITIVE LOGITS
     undoubtedly
    1.10
     called
    1.10
     definitely
    0.94
     probably
    0.94
    senal
    0.92
     usually
    0.87
     certainly
    0.84
     located
    0.82
     titled
    0.81
     invariably
    0.81
    Act Density 0.206%

    No Known Activations